© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53511
    Prev
    Next
    INDEX
    Explanations

    replace with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
    awy
    -0.09
    æľīè¿Ļæł·çļĦ
    -0.09
    æŀī
    -0.09
    rats
    -0.09
    fuse
    -0.08
    EXPR
    -0.08
    ä¸į解
    -0.08
    ersen
    -0.08
    æĤ¬
    -0.08
    POSITIVE LOGITS
     ones
    0.15
    ä»Ģä¹Īåij¢
    0.15
    æĽ´æľī
    0.15
    æĽ´éĢĤåIJĪ
    0.14
     something
    0.13
    æĽ´ä¸º
    0.13
    æĽ´å®¹æĺĵ
    0.12
    something
    0.12
    æį¢æĪIJ
    0.12
    æĽ´åĬł
    0.12
    Activations Density 0.092%

    No Known Activations